版权说明 操作指南
首页 > 成果 > 详情

Retinal optical coherence tomography image classification with label smoothing generative adversarial network

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
He, Xingxin;Fang, Leyuan;Rabbani, Hossein;Chen, Xiangdong;Liu, Zhimin
通讯作者:
Fang, LY
作者机构:
[He, Xingxin; Fang, Leyuan] Hunan Univ, Coll Elect & Informat Engn, Changsha, Hunan, Peoples R China.
[Rabbani, Hossein] Isfahan Univ Med Sci, Med Image & Signal Proc Res Ctr, Esfahan, Iran.
[Liu, Zhimin; Chen, Xiangdong] Hunan Univ Chinese Med, Affiliated Hosp 1, Dept Ophthalmol, Changsha, Peoples R China.
通讯机构:
[Fang, LY ] H
Hunan Univ, Coll Elect & Informat Engn, Changsha, Hunan, Peoples R China.
语种:
英文
关键词:
Classification (of information);Image enhancement;Ophthalmology;Optical tomography;Tomography;Adversarial networks;Age-related macular degeneration;Choroidal neovascularization;Classification performance;Limited training data;Retinal optical coherence tomography;Synthetic images;Training sample;Image classification;adult;age related macular degeneration;Article;artificial neural network;controlled study;diabetic macular edema;human;image analysis;image processing;information processing;label smoothing generative adversarial network;major clinical study;mathematical computing;mathematical model;optical coherence tomography;priority journal;process optimization;randomized controlled trial;retina examination;subretinal neovascularization
期刊:
Neurocomputing
ISSN:
0925-2312
年:
2020
卷:
405
页码:
37-47
基金类别:
The authors would like to thank Prof. Zhang from the Shiley Eye Institute of the University of California San Diego for providing the free download of the OCT dataset. This work was supported in part by the National Outstanding Youth Science Fund Project of National Natural Science Foundation of China under Grant No. 61922029, the National Natural Science Foundation of China under Grant No. 61771192, the Huxiang Young Talents Plan Project of Hunan Province under Grant No. 2019RS2016 and the Natural Science Foundation of Hunan Province under Grant No. 2018JJ3077. Leyuan Fang received Ph.D. degree from the College of Electrical and Information Engineering, Hunan University, Changsha, China, in 2015. From September 2011 to September 2012, he was a visiting Ph.D. student with the Department of Ophthalmology, Duke University, Durham, NC, USA, supported by the China Scholarship Council. From August 2016 to September 2017, he was a Postdoc Researcher with the Department of Biomedical Engineering, Duke University, Durham, NC, USA. He is currently a Professor with the College of Electrical and Information Engineering, Hunan University. His research interests include sparse representation and multi-resolution analysis in remote sensing and medical image processing. He was a recipient of one 2nd-Grade National Award at the Nature and Science Progress of China in 2019. This work was supported in part by the National Outstanding Youth Science Fund Project of National Natural Science Foundation of China under Grant No. 61922029 , the National Natural Science Foundation of China under Grant No. 61771192 , the Huxiang Young Talents Plan Project of Hunan Province under Grant No. 2019RS2016 and the Natural Science Foundation of Hunan Province under Grant No. 2018JJ3077 .
机构署名:
本校为其他机构
院系归属:
第一中医临床学院
摘要:
In this paper, we propose a label smoothing generative adversarial network (LSGAN) for optical coherence tomography (OCT) image classification to identify drusen, i.e., the early stage of age-related macular degeneration (AMD), choroidal neovascularization (CNV), diabetic macular edema (DME) and normal OCT images. The LSGAN can expand the dataset to address the issue of overfitting when only limited OCT training samples are available. Specifically, our LSGAN consists of three components: generator, discriminator, and classifier. The generator g...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com